Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5545 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.9226. Min Act: -0.1700
Data Index: 1119374 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.8601. Min Act: -0.1700
Data Index: 4455440 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.8288. Min Act: -0.1700
Data Index: 2241071 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.7819. Min Act: -0.1700
Data Index: 1767110 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.7819. Min Act: -0.1700
Data Index: 2559025 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.7819. Min Act: -0.1700
Data Index: 3640505 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6881. Min Act: -0.1700
Data Index: 7201219 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6724. Min Act: -0.1700
Data Index: 6903817 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6724. Min Act: -0.1700
Data Index: 4821424 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6568. Min Act: -0.1700
Data Index: 1253136 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6411. Min Act: -0.1700
Data Index: 4112960 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.6098. Min Act: -0.1700
Data Index: 2504917 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5942. Min Act: -0.1700
Data Index: 1474177 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5942. Min Act: -0.1700
Data Index: 1885276 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5942. Min Act: -0.1700
Data Index: 7816723 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5629. Min Act: -0.1700
Data Index: 1767111 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5629. Min Act: -0.1700
Data Index: 8734105 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5629. Min Act: -0.1700
Data Index: 1454976 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5472. Min Act: -0.1700
Data Index: 3082602 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9226. Min Range: -3.9226
Max Act: 3.5316. Min Act: -0.1700
Data Index: 8436899 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19